{"id":"W4293193531","doi":"10.1109/access.2022.3170897","title":"A Deep Attentive Multimodal Learning Approach for Disaster Identification From Social Media Posts","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Social media; Identification (biology); Artificial intelligence; Recurrent neural network; Softmax function; Microblogging; Classifier (UML); Deep learning; Modality (human–computer interaction); Machine learning; Artificial neural network; Information retrieval; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004043383,0.001091415,0.0005254408,0.0009509578,0.0003617845,0.0004312344,0.0008473785,0.0008040442,0.002834823],"category_scores_gemma":[0.000917157,0.0002622343,0.0006412629,0.0006184964,0.00030952,0.001334907,0.001201706,0.001023423,0.001053303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004962646,"about_ca_system_score_gemma":0.0004883357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003623391,"about_ca_topic_score_gemma":0.00702152,"domain_scores_codex":[0.9997563,0.00003749686,0.00001209031,0.00008990416,0.00004788065,0.00005633988],"domain_scores_gemma":[0.9997969,0.00005576373,0.00002852136,0.0000230211,0.00007077062,0.00002501464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000653685,0.000844778,0.005082798,0.0002267494,0.000189183,0.0005215377,0.0003832336,0.06510698,0.05425362,0.002096908,0.01070887,0.8599316],"study_design_scores_gemma":[0.00001467445,0.0002584335,0.002615484,0.00002414989,0.00007649646,0.0001132757,0.0001267162,0.979813,0.01152378,0.002828588,0.00257616,0.0000293196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2029187,0.001787773,0.775929,0.0009328767,0.0003469733,0.000303716,0.001022214,0.007143005,0.009615709],"genre_scores_gemma":[0.8788741,0.0004930823,0.1057193,0.0004696412,0.0001917436,0.0001849916,0.001136608,0.00009881237,0.0128317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003623391,"threshold_uncertainty_score":0.009483457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06028547662032377,"score_gpt":0.3600284143139184,"score_spread":0.2997429376935946,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}